The UK government’s AI Security Institute: evaluations, red-teaming and research on frontier AI risks. aisi.gov.uk
Studies AI control against distributed multi-agent attacks, finding per-agent monitors catch fewer attackers as agents coordinate, and that stronger trusted monitors reduce undetected attacks.
Evaluates lie detectors (CoT judge, logprob classifier, activation probes, new Did-You-Lie probes) on belief-verified model organisms and 31 models; activation methods degrade on trained organisms while CoT judge stays strong.
Proposes a decision-theoretic formalisation of steganography and a "steganographic gap" metric to detect and quantify hidden reasoning in LLMs that could evade monitoring.
Position piece arguing chain-of-thought monitoring offers a fragile but valuable way to catch AI misbehaviour, and recommending further research and developer attention to preserving CoT monitorability.
UK AISI's White Box Control team shares preliminary results on sandbagging investigations, using internal model inspection to detect models deliberately underperforming.